Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.6178. Min Act: -0.1700
Data Index: 7784353 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.6178. Min Act: -0.1700
Data Index: 2186790 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.5553. Min Act: -0.1700
Data Index: 1364904 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.5240. Min Act: -0.1700
Data Index: 538926 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4928. Min Act: -0.1700
Data Index: 6363866 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4928. Min Act: -0.1700
Data Index: 7175828 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4615. Min Act: -0.1700
Data Index: 8302482 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1188529 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 4773683 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4303. Min Act: -0.1700
Data Index: 8568418 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.4615. Min Act: -0.1700
Data Index: 2089896 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 3782931 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 5446398 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1010515 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1699612 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3678. Min Act: -0.1700
Data Index: 1010514 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3990. Min Act: -0.1700
Data Index: 7693080 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3678. Min Act: -0.1700
Data Index: 7592638 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3678. Min Act: -0.1700
Data Index: 1699608 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6178. Min Range: -5.6178
Max Act: 5.3678. Min Act: -0.1700
Data Index: 2481849 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19